rbelanec commited on
Commit
686db8c
verified
1 Parent(s): 61a985a

Training in progress, step 40000

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +42 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df98bab001bda54ee9af7995045f74825831a8ffe9c0213ed6c6d7b561891d50
3
  size 498936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b58b7897130b11dbf054d150cda863f53cbc60e9026c5ab850f1242b215909dc
3
  size 498936
trainer_log.jsonl CHANGED
@@ -8157,3 +8157,45 @@
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0923, "lr": 3.2720109079037443e-09, "epoch": 1.94442137150954, "percentage": 99.49, "elapsed_time": "1 day, 3:45:53", "remaining_time": "0:08:34", "throughput": 516.14, "total_tokens": 51590464}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.077, "lr": 3.1151063006468193e-09, "epoch": 1.9446656731732344, "percentage": 99.5, "elapsed_time": "1 day, 3:45:57", "remaining_time": "0:08:22", "throughput": 516.19, "total_tokens": 51597120}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.08723117411136627, "epoch": 1.9446656731732344, "percentage": 99.5, "elapsed_time": "1 day, 3:52:11", "remaining_time": "0:08:24", "throughput": 514.26, "total_tokens": 51597120}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0923, "lr": 3.2720109079037443e-09, "epoch": 1.94442137150954, "percentage": 99.49, "elapsed_time": "1 day, 3:45:53", "remaining_time": "0:08:34", "throughput": 516.14, "total_tokens": 51590464}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.077, "lr": 3.1151063006468193e-09, "epoch": 1.9446656731732344, "percentage": 99.5, "elapsed_time": "1 day, 3:45:57", "remaining_time": "0:08:22", "throughput": 516.19, "total_tokens": 51597120}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.08723117411136627, "epoch": 1.9446656731732344, "percentage": 99.5, "elapsed_time": "1 day, 3:52:11", "remaining_time": "0:08:24", "throughput": 514.26, "total_tokens": 51597120}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.0683, "lr": 2.962056527169854e-09, "epoch": 1.9449099748369285, "percentage": 99.51, "elapsed_time": "1 day, 3:52:16", "remaining_time": "0:08:11", "throughput": 514.31, "total_tokens": 51604032}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.085, "lr": 2.8128616110761898e-09, "epoch": 1.945154276500623, "percentage": 99.52, "elapsed_time": "1 day, 3:52:19", "remaining_time": "0:07:58", "throughput": 514.36, "total_tokens": 51610464}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0949, "lr": 2.6675215753724223e-09, "epoch": 1.9453985781643173, "percentage": 99.54, "elapsed_time": "1 day, 3:52:23", "remaining_time": "0:07:46", "throughput": 514.4, "total_tokens": 51616928}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.0874, "lr": 2.5260364424739557e-09, "epoch": 1.9456428798280117, "percentage": 99.55, "elapsed_time": "1 day, 3:52:26", "remaining_time": "0:07:33", "throughput": 514.45, "total_tokens": 51623520}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0902, "lr": 2.3884062341994475e-09, "epoch": 1.945887181491706, "percentage": 99.56, "elapsed_time": "1 day, 3:52:29", "remaining_time": "0:07:20", "throughput": 514.5, "total_tokens": 51630240}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.125, "lr": 2.25463097177081e-09, "epoch": 1.9461314831554004, "percentage": 99.58, "elapsed_time": "1 day, 3:52:32", "remaining_time": "0:07:08", "throughput": 514.56, "total_tokens": 51637152}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.0593, "lr": 2.1247106758215397e-09, "epoch": 1.9463757848190946, "percentage": 99.59, "elapsed_time": "1 day, 3:52:35", "remaining_time": "0:06:55", "throughput": 514.61, "total_tokens": 51643648}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0884, "lr": 1.998645366382834e-09, "epoch": 1.946620086482789, "percentage": 99.6, "elapsed_time": "1 day, 3:52:38", "remaining_time": "0:06:43", "throughput": 514.66, "total_tokens": 51650272}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.1198, "lr": 1.876435062897475e-09, "epoch": 1.9468643881464833, "percentage": 99.61, "elapsed_time": "1 day, 3:52:42", "remaining_time": "0:06:30", "throughput": 514.71, "total_tokens": 51657024}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0912, "lr": 1.758079784211497e-09, "epoch": 1.9471086898101775, "percentage": 99.62, "elapsed_time": "1 day, 3:52:45", "remaining_time": "0:06:17", "throughput": 514.75, "total_tokens": 51663424}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0806, "lr": 1.6435795485797434e-09, "epoch": 1.9473529914738719, "percentage": 99.64, "elapsed_time": "1 day, 3:52:48", "remaining_time": "0:06:05", "throughput": 514.8, "total_tokens": 51669824}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.1017, "lr": 1.5329343736547596e-09, "epoch": 1.9475972931375662, "percentage": 99.65, "elapsed_time": "1 day, 3:52:51", "remaining_time": "0:05:52", "throughput": 514.85, "total_tokens": 51676448}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0756, "lr": 1.4261442765006739e-09, "epoch": 1.9478415948012606, "percentage": 99.66, "elapsed_time": "1 day, 3:52:54", "remaining_time": "0:05:39", "throughput": 514.9, "total_tokens": 51683328}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0855, "lr": 1.3232092735876445e-09, "epoch": 1.948085896464955, "percentage": 99.67, "elapsed_time": "1 day, 3:52:58", "remaining_time": "0:05:27", "throughput": 514.95, "total_tokens": 51689248}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0927, "lr": 1.2241293807918607e-09, "epoch": 1.9483301981286494, "percentage": 99.69, "elapsed_time": "1 day, 3:53:01", "remaining_time": "0:05:14", "throughput": 515.0, "total_tokens": 51695968}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0616, "lr": 1.128904613387216e-09, "epoch": 1.9485744997923435, "percentage": 99.7, "elapsed_time": "1 day, 3:53:04", "remaining_time": "0:05:02", "throughput": 515.05, "total_tokens": 51702816}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0802, "lr": 1.0375349860591853e-09, "epoch": 1.948818801456038, "percentage": 99.71, "elapsed_time": "1 day, 3:53:07", "remaining_time": "0:04:49", "throughput": 515.1, "total_tokens": 51709184}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.1086, "lr": 9.5002051290205e-10, "epoch": 1.9490631031197323, "percentage": 99.72, "elapsed_time": "1 day, 3:53:10", "remaining_time": "0:04:36", "throughput": 515.15, "total_tokens": 51715904}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.1014, "lr": 8.663612074077954e-10, "epoch": 1.9493074047834265, "percentage": 99.74, "elapsed_time": "1 day, 3:53:13", "remaining_time": "0:04:24", "throughput": 515.19, "total_tokens": 51722016}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0606, "lr": 7.865570824799884e-10, "epoch": 1.9495517064471208, "percentage": 99.75, "elapsed_time": "1 day, 3:53:17", "remaining_time": "0:04:11", "throughput": 515.24, "total_tokens": 51728128}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0649, "lr": 7.106081504254514e-10, "epoch": 1.9497960081108152, "percentage": 99.76, "elapsed_time": "1 day, 3:53:20", "remaining_time": "0:03:59", "throughput": 515.28, "total_tokens": 51734368}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.081, "lr": 6.385144229570372e-10, "epoch": 1.9500403097745096, "percentage": 99.78, "elapsed_time": "1 day, 3:53:23", "remaining_time": "0:03:46", "throughput": 515.33, "total_tokens": 51740768}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0991, "lr": 5.70275911190854e-10, "epoch": 1.950284611438204, "percentage": 99.79, "elapsed_time": "1 day, 3:53:26", "remaining_time": "0:03:33", "throughput": 515.38, "total_tokens": 51748000}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0834, "lr": 5.058926256490403e-10, "epoch": 1.9505289131018984, "percentage": 99.8, "elapsed_time": "1 day, 3:53:29", "remaining_time": "0:03:21", "throughput": 515.43, "total_tokens": 51754432}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0551, "lr": 4.4536457626254134e-10, "epoch": 1.9507732147655925, "percentage": 99.81, "elapsed_time": "1 day, 3:53:33", "remaining_time": "0:03:08", "throughput": 515.48, "total_tokens": 51761120}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.1012, "lr": 3.88691772365557e-10, "epoch": 1.951017516429287, "percentage": 99.83, "elapsed_time": "1 day, 3:53:36", "remaining_time": "0:02:56", "throughput": 515.53, "total_tokens": 51767712}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0916, "lr": 3.358742226955425e-10, "epoch": 1.951261818092981, "percentage": 99.84, "elapsed_time": "1 day, 3:53:39", "remaining_time": "0:02:43", "throughput": 515.58, "total_tokens": 51773824}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.086, "lr": 2.8691193539875925e-10, "epoch": 1.9515061197566754, "percentage": 99.85, "elapsed_time": "1 day, 3:53:42", "remaining_time": "0:02:30", "throughput": 515.62, "total_tokens": 51780064}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0958, "lr": 2.418049180274995e-10, "epoch": 1.9517504214203698, "percentage": 99.86, "elapsed_time": "1 day, 3:53:45", "remaining_time": "0:02:18", "throughput": 515.67, "total_tokens": 51786752}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0896, "lr": 2.005531775373104e-10, "epoch": 1.9519947230840642, "percentage": 99.88, "elapsed_time": "1 day, 3:53:48", "remaining_time": "0:02:05", "throughput": 515.72, "total_tokens": 51793056}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0908, "lr": 1.6315672028699435e-10, "epoch": 1.9522390247477586, "percentage": 99.89, "elapsed_time": "1 day, 3:53:52", "remaining_time": "0:01:53", "throughput": 515.77, "total_tokens": 51799552}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0827, "lr": 1.2961555204693555e-10, "epoch": 1.952483326411453, "percentage": 99.9, "elapsed_time": "1 day, 3:53:55", "remaining_time": "0:01:40", "throughput": 515.81, "total_tokens": 51805824}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0925, "lr": 9.992967798799768e-11, "epoch": 1.9527276280751473, "percentage": 99.91, "elapsed_time": "1 day, 3:53:58", "remaining_time": "0:01:27", "throughput": 515.86, "total_tokens": 51812544}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0544, "lr": 7.409910268707521e-11, "epoch": 1.9529719297388415, "percentage": 99.92, "elapsed_time": "1 day, 3:54:01", "remaining_time": "0:01:15", "throughput": 515.92, "total_tokens": 51819520}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0668, "lr": 5.212383012986877e-11, "epoch": 1.9532162314025359, "percentage": 99.94, "elapsed_time": "1 day, 3:54:04", "remaining_time": "0:01:02", "throughput": 515.97, "total_tokens": 51826336}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.1011, "lr": 3.400386370533415e-11, "epoch": 1.95346053306623, "percentage": 99.95, "elapsed_time": "1 day, 3:54:07", "remaining_time": "0:00:50", "throughput": 516.02, "total_tokens": 51833216}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.1078, "lr": 1.9739206205682258e-11, "epoch": 1.9537048347299244, "percentage": 99.96, "elapsed_time": "1 day, 3:54:11", "remaining_time": "0:00:37", "throughput": 516.07, "total_tokens": 51840096}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0734, "lr": 9.329859829154685e-12, "epoch": 1.9539491363936188, "percentage": 99.98, "elapsed_time": "1 day, 3:54:14", "remaining_time": "0:00:25", "throughput": 516.12, "total_tokens": 51846688}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0811, "lr": 2.7758261855748148e-12, "epoch": 1.9541934380573132, "percentage": 99.99, "elapsed_time": "1 day, 3:54:17", "remaining_time": "0:00:12", "throughput": 516.16, "total_tokens": 51852640}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.071, "lr": 7.710628524559838e-14, "epoch": 1.9544377397210075, "percentage": 100.0, "elapsed_time": "1 day, 3:54:20", "remaining_time": "0:00:00", "throughput": 516.21, "total_tokens": 51858816}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.08723115921020508, "epoch": 1.9544377397210075, "percentage": 100.0, "elapsed_time": "1 day, 4:00:35", "remaining_time": "0:00:00", "throughput": 514.29, "total_tokens": 51858816}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 1.9544377397210075, "percentage": 100.0, "elapsed_time": "1 day, 4:00:36", "remaining_time": "0:00:00", "throughput": 514.28, "total_tokens": 51858816}